lark-integration
Connect Lark (Feishu) messaging to OpenClaw via webhook bridge. Supports text, rich text (post), and image messages bidirectionally. Use when setting up Lark/Feishu as a messaging channel, receiving messages with images, sending replies back to Lark, reading Lark documents/wikis/bitables, or troubleshooting Lark integration issues. Covers both Lark International (larksuite.com) and China Feishu (feishu.cn).
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/boyangwang/lark-integrationWhat This Skill Does
The lark-integration skill serves as a robust middleware bridge between the Lark (or Feishu) messaging ecosystem and your OpenClaw agent. It functions as a bidirectional webhook handler, enabling seamless communication flow. When a user sends a message or interacts with your bot in Lark, this skill captures the event, decrypts it if necessary, and forwards it to the OpenClaw gateway. It handles complex message types including plain text, rich text (post) objects, and image attachments. When the OpenClaw agent generates a response, this skill translates that output back into a format Lark understands, ensuring your bot remains responsive and capable of handling complex interactions directly within your team's favorite messaging platform.
Installation
To integrate this skill, ensure you have the OpenClaw environment properly configured. First, install the skill package via the command line using clawhub install openclaw/skills/skills/boyangwang/lark-integration. Next, generate an App ID and App Secret from the Lark Developer Console. You must set these in your .openclaw/workspace/.env file and store the secret in the designated directory at ~/.openclaw/secrets/feishu_app_secret. After completing the setup, execute node scripts/bridge-webhook.mjs to initiate the bridge process. For production deployments, it is highly recommended to run node scripts/setup-service.mjs to ensure the bridge runs as a persistent systemd service, guaranteeing high availability for your bot's communications.
Use Cases
- Automated Customer Support: Automatically route help requests from Lark to your AI agent and receive instant, structured responses.
- Content Extraction: Use the built-in document and wiki support to pull data from internal company resources for analysis by your agent.
- Image-based Tasking: Users can snap photos of whiteboard notes or physical forms and send them to the agent for digitization or summarization.
- Workflow Orchestration: Trigger complex backend processes in OpenClaw simply by typing commands within a Lark chat window.
Example Prompts
- "Hey agent, check the latest project document in the Wiki and summarize the current bottlenecks for the dev team."
- [User attaches an image of a handwritten checklist] "Can you parse this checklist and convert it into a tracking table in our internal Bitable?"
- "Please send a weekly summary of these chat discussions to the general project channel in Lark."
Tips & Limitations
- Permissions: Always review the Scopes section in the Lark Developer Console; the bot will fail to process specific requests like 'Read Wiki' if the correct OAuth scopes are not enabled.
- Thinking Delay: If your agent requires heavy computation, adjust the
FEISHU_THINKING_THRESHOLD_MSto prevent timeout errors from the Lark webhook server. - Rich Text: While the bridge supports rich text, complex card layouts are best managed via the dedicated
feishu-cardskill if you require highly interactive buttons or input forms.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-boyangwang-lark-integration": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api